May 9, 2016
期末報告
組別/報告日期 – 大四
5/30: 雙北市新興旅店，你就是錢老闆*3 –種類，旅客來源，
影響因子（交通？平台？）- 6/6:
- 臺北市道路速率資料分析 *4 –地理位置/時間/
天氣 - 台北市的黃金單車路線 *2 –位置/設施/空汙
- 台灣交通事故統計資料分析 *4 –時間/車種/嚴重程度/原因/
地理位置 - 小老婆汽機車資訊網 機車資訊調查 *3 –FB評論/事故（
輕重、種類...）
- 臺北市道路速率資料分析 *4 –地理位置/時間/
組別/報告日期 – 照作業繳交時間安排
- 6/13:
- Marvel 101 *1 – 角色能力/出場次數/漫畫章節數（
關連性？影響因子） - 地震與雨量真的有關係嗎? *2 – 雨量/地震（
地震震源位置/深淺） - 分析教育程度與各行各業的關係 *3 – 學歷/就業（
主修種類、年紀、性別） - Facebook粉專分析 *3 – 按讚數/留言數與留言本身的關係（
留言分類？）
- Marvel 101 *1 – 角色能力/出場次數/漫畫章節數（
組別/報告日期 – 運動組
新的資料來源
期末報告規定
報告
15-20分鐘，問問題5分鐘 —> 講重點，嚴格計時- 整組交一份書面報告
- 組員與工作分配（會影響成績）
- 資料分析報告
- 資料討論/遇到的困難
- 回答報告時被問的問題
作業問題
- 若資料的更新頻率是"每五分鐘"，"每天"
- 請寫程式或人工把需要的時間區間資料取回
資料格式：表格？圖表？—若已經是圖表，就不用做報告了…..
若資料是JSON, XML，請務必要儘速測試資料是否能順利讀取
作業的複雜程度與組員人數盡量成正比，會斟酌加減分
ggplot2 還能畫更多圖
Choropleth map 面量圖
choroplethr & choroplethrMaps packages 
Choropleth map
- 面量圖
- 把統計資料用顏色畫在對應的地圖上
choroplethr&choroplethrMapspackages- 基於
ggplot2package所做的專門畫面量圖的工具
if (!require('choroplethr')){
install.packages("choroplethr")
library(choroplethr) ## for state_choropleth()
}
if (!require('choroplethrMaps')){
install.packages("choroplethrMaps") ##上次沒有安裝到這個package
library(choroplethrMaps) ## for state_choropleth()
}
美國各州人口分布
用到choroplethr & choroplethrMaps packages, 記得先讀入
data(df_pop_state) #記載各州人口數的資料 state_choropleth(df_pop_state) #把各州人口畫在地圖上
Taiwan的面量圖
- 使用
rgdal,rgeos,maptoolspackage處理地圖檔 - 使用
ggplot2&RColorBrewer畫圖
Taiwan的面量圖
將shapefile讀入R
使用maptools package 的readShapeSpatial function
if (!require('rgdal')){#for fortify()
install.packages("rgdal");library(rgdal)
}
if (!require('rgeos')){#for fortify()
install.packages("rgeos");library(rgeos)
}
if (!require('maptools')){#for readShapeSpatial()
install.packages("maptools");library(maptools)
}
tw_new <- readShapeSpatial("Taiwan/Town_MOI_1041215.shp") #檔名
names(tw_new)
## [1] "OBJECTID" "T_UID" "Town_ID" "T_Name" "T_Desc" ## [6] "Add_Date" "Add_Accept" "Remark" "County_ID" "C_Name"
處理shapefile-1
- 需要
rgdal,rgeos,maptools - fortify: 將
shapefile物件轉為data.frame - 參考資料
library(ggplot2) #for fortify(), ggplot(), ggmap() head(tw_new$Town_ID)
## [1] 1001402 1001321 1000913 1001411 1001416 1000712 ## 368 Levels: 0900701 0900702 0900703 0900704 0902001 0902002 ... 6801300
tw_new.df <- fortify(tw_new, region = "T_UID") #from ggplot2 package
處理shapefile-2
head(tw_new.df,10)
## long lat order hole piece id group ## 1 119.9170 26.17518 1 FALSE 1 1 1.1 ## 2 119.9171 26.17517 2 FALSE 1 1 1.1 ## 3 119.9171 26.17518 3 FALSE 1 1 1.1 ## 4 119.9171 26.17518 4 FALSE 1 1 1.1 ## 5 119.9171 26.17518 5 FALSE 1 1 1.1 ## 6 119.9172 26.17518 6 FALSE 1 1 1.1 ## 7 119.9172 26.17518 7 FALSE 1 1 1.1 ## 8 119.9172 26.17518 8 FALSE 1 1 1.1 ## 9 119.9173 26.17515 9 FALSE 1 1 1.1 ## 10 119.9173 26.17515 10 FALSE 1 1 1.1
做一個假資料來畫：著色基準檔
#做一個假資料來畫
#prevalence設為亂數rnorm(需要的亂數個數)
mydata<-data.frame(NAME_2=tw_new$T_Name, id=tw_new$T_UID,
prevalence=rnorm(length(tw_new$T_UID)))
head(mydata)
## NAME_2 id prevalence ## 1 \xa6\xa8\xa5\\\xc2\xed 178 -1.0704142 ## 2 \xa8ΥV\xb6m 164 -1.6089234 ## 3 \xb3\xc1\xbcd\xb6m 118 2.0302805 ## 4 \xba\xf1\xaeq\xb6m 376 1.6737724 ## 5 \xc4\xf5\xc0\xac\xb6m 369 0.5319908 ## 6 \xa5Ф\xa4\xc2\xed 78 0.7070405
中文編碼
#利用iconv將不知所以然的代碼（\xa6\xa8\xa5\\\xc2\xed）轉為看得懂的中文
#from big5 to utf-8
mydata$NAME_2<-iconv(as.character(mydata$NAME_2), #NAME_2原本是factor
from="big5", to = "UTF-8")
head(mydata,10)
## NAME_2 id prevalence ## 1 成功鎮 178 -1.07041422 ## 2 佳冬鄉 164 -1.60892338 ## 3 麥寮鄉 118 2.03028055 ## 4 綠島鄉 376 1.67377244 ## 5 蘭嶼鄉 369 0.53199077 ## 6 田中鎮 78 0.70704051 ## 7 社頭鄉 83 1.18218352 ## 8 竹田鄉 157 0.35104423 ## 9 萬丹鄉 148 -0.06741472 ## 10 三灣鄉 64 -0.27611486
合併的圖檔與著色基準檔
#最後將有prevalence的假數據mydata和經緯度資料tw_new.df合併, 用merge() final.plot<-merge(tw_new.df,mydata,by="id",all.x=T) head(final.plot,10)
## id long lat order hole piece group NAME_2 prevalence ## 1 1 119.9170 26.17518 1 FALSE 1 1.1 南竿鄉 -2.277062 ## 2 1 119.9171 26.17517 2 FALSE 1 1.1 南竿鄉 -2.277062 ## 3 1 119.9171 26.17518 3 FALSE 1 1.1 南竿鄉 -2.277062 ## 4 1 119.9171 26.17518 4 FALSE 1 1.1 南竿鄉 -2.277062 ## 5 1 119.9171 26.17518 5 FALSE 1 1.1 南竿鄉 -2.277062 ## 6 1 119.9172 26.17518 6 FALSE 1 1.1 南竿鄉 -2.277062 ## 7 1 119.9172 26.17518 7 FALSE 1 1.1 南竿鄉 -2.277062 ## 8 1 119.9172 26.17518 8 FALSE 1 1.1 南竿鄉 -2.277062 ## 9 1 119.9173 26.17515 9 FALSE 1 1.1 南竿鄉 -2.277062 ## 10 1 119.9173 26.17515 10 FALSE 1 1.1 南竿鄉 -2.277062
畫台灣面量圖-1
library(RColorBrewer) #配色用brewer.pal( 9 , "Reds" )
twcmap<-ggplot() +
geom_polygon(data = final.plot,
aes(x = long, y = lat, group = group,
fill = prevalence),
color = "black", size = 0.25) +
coord_map()+#維持地圖比例
scale_fill_gradientn(colours = brewer.pal(9,"Reds"))+
theme_void()+
labs(title="Prevalence of X in Taiwan")
畫台灣面量圖-2
twcmap
使用google map
ggmap package 
ggmap，把google map載入
if (!require('ggmap')){
install.packages("ggmap")
library(ggmap)#for get_map()
}
twmap <- get_map(location = 'Taiwan', zoom = 7,language = "zh-TW")
#location:可以是地名，也可以是經緯度座標
#zoom:放大比例 2-20
#language:地圖語言
ggmap，畫圖
ggmap(twmap) #基於ggplot2物件，可用相同方式處理
ggmap，maptype
#maptype:地圖型態，"terrain", "terrain-background", "satellite",
# "roadmap","hybrid" (google maps), "terrain", "watercolor",
# "toner" (stamen maps),
# or a positive integer for cloudmade maps (see ?get_cloudmademap)
TaipeiMap = get_map(location = c(121.43,24.93,121.62,25.19),
zoom = 14, maptype = 'roadmap')
ggmap(TaipeiMap,extent = 'device') #extent = 'device' 滿版
ggmap+面量圖
ggmap(twmap)+ #ggmap
geom_polygon(data = final.plot, #面量圖
aes(x = long, y = lat, group = group, fill = prevalence),
color = "grey80", size = 0.1,alpha = 0.5) +
scale_fill_gradientn(colours = brewer.pal(9,"Reds"))
Density Map? 美國人口密度圖
使用 ggplot2 + ggmap 來畫人口密度圖 - 資料前處理1
#取得美國各州中心座標資料
StateCenter<-data.frame(
region=tolower(state.name),lon=state.center$x,lat=state.center$y)
head(StateCenter,1)
## region lon lat ## 1 alabama -86.7509 32.5901
#美國各州人口資料 StatePop<-merge(df_pop_state,StateCenter,by="region") head(StatePop,1)
## region value lon lat ## 1 alabama 4777326 -86.7509 32.5901
使用 ggplot2 + ggmap 來畫人口密度圖 - 資料前處理2
#將人口數值，轉為點！重要！
PopPoint<-NULL
for(i in 1:nrow(StatePop)){
#每100萬人轉為1點
for(j in 1:(StatePop[i,"value"]/1000000)){
PopPoint<-rbind(PopPoint,StatePop[i,])
}
}
head(PopPoint,3)
## region value lon lat ## 1 alabama 4777326 -86.7509 32.5901 ## 2 alabama 4777326 -86.7509 32.5901 ## 3 alabama 4777326 -86.7509 32.5901
使用 ggplot2 + ggmap 來畫人口密度圖 - 作圖
USMap <- get_map(location = "United States", zoom = 4)
densityMap<-ggmap(USMap, extent = "device") +
geom_density2d(data = PopPoint, aes(x = lon, y = lat), size = 0.3) +
stat_density2d(data = PopPoint,
aes(x = lon, y = lat, fill = ..level.., alpha = ..level..),
size = 0.01, bins = 16, geom = "polygon") +
scale_fill_gradient(low = "green", high = "red", guide = FALSE) +
scale_alpha(range = c(0, 0.3), guide = FALSE)
美國人口密度圖 Density Map
densityMap
ggmap參考資料
Heatmap 先將資料讀入
#讀.csv檔案
nba <- read.csv("http://datasets.flowingdata.com/ppg2008.csv")
head(nba)
## Name G MIN PTS FGM FGA FGP FTM FTA FTP X3PM X3PA ## 1 Dwyane Wade 79 38.6 30.2 10.8 22.0 0.491 7.5 9.8 0.765 1.1 3.5 ## 2 LeBron James 81 37.7 28.4 9.7 19.9 0.489 7.3 9.4 0.780 1.6 4.7 ## 3 Kobe Bryant 82 36.2 26.8 9.8 20.9 0.467 5.9 6.9 0.856 1.4 4.1 ## 4 Dirk Nowitzki 81 37.7 25.9 9.6 20.0 0.479 6.0 6.7 0.890 0.8 2.1 ## 5 Danny Granger 67 36.2 25.8 8.5 19.1 0.447 6.0 6.9 0.878 2.7 6.7 ## 6 Kevin Durant 74 39.0 25.3 8.9 18.8 0.476 6.1 7.1 0.863 1.3 3.1 ## X3PP ORB DRB TRB AST STL BLK TO PF ## 1 0.317 1.1 3.9 5.0 7.5 2.2 1.3 3.4 2.3 ## 2 0.344 1.3 6.3 7.6 7.2 1.7 1.1 3.0 1.7 ## 3 0.351 1.1 4.1 5.2 4.9 1.5 0.5 2.6 2.3 ## 4 0.359 1.1 7.3 8.4 2.4 0.8 0.8 1.9 2.2 ## 5 0.404 0.7 4.4 5.1 2.7 1.0 1.4 2.5 3.1 ## 6 0.422 1.0 5.5 6.5 2.8 1.3 0.7 3.0 1.8
Heatmap 資料處理，寬表轉長表
library(reshape2) #for melt() nba.m <- melt(nba,id.vars = "Name") #寬表轉長表,以名字作依據 head(nba.m,10)
## Name variable value ## 1 Dwyane Wade G 79 ## 2 LeBron James G 81 ## 3 Kobe Bryant G 82 ## 4 Dirk Nowitzki G 81 ## 5 Danny Granger G 67 ## 6 Kevin Durant G 74 ## 7 Kevin Martin G 51 ## 8 Al Jefferson G 50 ## 9 Chris Paul G 78 ## 10 Carmelo Anthony G 66
Heatmap geom_tile()
library(ggplot2) #for ggplot()
ggplot(nba.m, aes(variable, Name)) + #aes(x,y)
geom_tile(aes(fill = value),colour = "white")+ #geom_tile: 區塊著色
scale_fill_gradient(low = "white",high = "steelblue") #數值低：白色
Heatmap 資料前處理：scale
head(nba,2)
## Name G MIN PTS FGM FGA FGP FTM FTA FTP X3PM X3PA X3PP ## 1 Dwyane Wade 79 38.6 30.2 10.8 22.0 0.491 7.5 9.8 0.765 1.1 3.5 0.317 ## 2 LeBron James 81 37.7 28.4 9.7 19.9 0.489 7.3 9.4 0.780 1.6 4.7 0.344 ## ORB DRB TRB AST STL BLK TO PF ## 1 1.1 3.9 5.0 7.5 2.2 1.3 3.4 2.3 ## 2 1.3 6.3 7.6 7.2 1.7 1.1 3.0 1.7
nba[,2:21]<-apply(nba[,2:21], 2, scale) #scale處理，將數值轉為平均=0 head(nba,2)
## Name G MIN PTS FGM FGA FGP ## 1 Dwyane Wade 0.6179300 1.0019702 3.179941 2.920022 2.596832 0.5136017 ## 2 LeBron James 0.7693834 0.6119299 2.566974 1.957185 1.697237 0.4649190 ## FTM FTA FTP X3PM X3PA X3PP ## 1 1.917475 2.110772 -0.7401673 -0.1080044 0.1303647 -0.15749098 ## 2 1.778729 1.896589 -0.5233214 0.4920201 0.6971679 0.02738974 ## ORB DRB TRB AST STL BLK TO ## 1 -0.27213551 -0.3465676 -0.3287465 1.652247 2.558238 1.2064646 1.790445 ## 2 -0.06117775 1.0080940 0.6605370 1.516147 1.367252 0.8627425 1.059651 ## PF ## 1 -0.2984568 ## 2 -1.3903719
apply() 還記得嗎….
有類似for迴圈的功能
- apply(Data, MARGIN, FUN,…)
- Data：矩陣（Matrix），Data Frame
- MARGIN：1=row, 2=column
- FUN：函數
- …：函數要用的參數
#針對nba的各column做scale處理-->將數值轉為平均=0 apply(nba[,2:21], 2, scale)
## G MIN PTS FGM FGA ## [1,] 0.61793000 1.001970241 3.17994147 2.92002219 2.59683207 ## [2,] 0.76938343 0.611929922 2.56697353 1.95718513 1.69723666 ## [3,] 0.84511015 -0.038137276 2.02211313 2.04471578 2.12561543 ## [4,] 0.76938343 0.611929922 1.71562916 1.86965449 1.74007454 ## [5,] -0.29079059 -0.038137276 1.68157539 0.90681744 1.35453365 ## [6,] 0.23929642 1.175321493 1.51130651 1.25694001 1.22602002 ## [7,] -1.50241804 0.828618988 1.27293009 -0.66873410 -0.01627839 ## [8,] -1.57814476 0.135213977 0.76212347 1.95718513 1.52588516 ## [9,] 0.54220328 0.958632428 0.65996215 0.55669488 0.06939736 ## [10,] -0.36651730 -0.774880100 0.65996215 0.55669488 1.01183064 ## [11,] 0.46647657 0.785281175 0.62590838 0.46916424 0.19791099 ## [12,] 0.54220328 0.395240856 0.59185460 0.55669488 0.41210037 ## [13,] 0.76938343 0.828618988 0.45563950 0.73175616 0.79764126 ## [14,] 0.08784299 -0.948231352 0.38753195 1.25694001 0.66912763 ## [15,] -1.35096461 0.221889603 0.18320931 0.11904167 -0.78736017 ## [16,] 0.61793000 1.392010559 0.18320931 0.29410295 0.88331701 ## [17,] -0.13933716 -0.081475089 0.14915553 -0.75626474 -0.35898140 ## [18,] -2.86549892 0.048538351 0.11510176 0.03151103 0.28358674 ## [19,] 0.39074985 1.305334933 0.04699421 0.46916424 0.45493825 ## [20,] -1.57814476 -0.514853221 -0.02111334 0.73175616 0.66912763 ## [21,] -0.29079059 1.001970241 -0.02111334 -0.14355025 0.11223524 ## [22,] 0.69365672 0.221889603 -0.02111334 -0.05601961 0.36926249 ## [23,] -0.89660431 1.478686186 -0.05516711 -0.40614217 0.41210037 ## [24,] 0.84511015 0.135213977 -0.05516711 -0.14355025 0.02655948 ## [25,] 0.61793000 -0.254826342 -0.08922089 -0.31861153 -1.51560407 ## [26,] 0.76938343 0.481916483 -0.12327466 -0.66873410 -0.57317079 ## [27,] 0.16356971 -0.601528847 -0.25948976 -0.14355025 0.28358674 ## [28,] -0.44224402 0.785281175 -0.39570486 -0.93132602 -0.10195415 ## [29,] 0.46647657 -1.164920418 -0.39570486 -0.05601961 -1.08722530 ## [30,] 0.84511015 -0.168150715 -0.42975863 -0.84379538 -0.44465716 ## [31,] 0.23929642 -1.164920418 -0.42975863 -0.14355025 -0.05911627 ## [32,] -0.21506387 0.265227417 -0.49786618 -0.58120346 -0.61600866 ## [33,] 0.31502314 -1.121582605 -0.53191996 -0.05601961 -0.48749503 ## [34,] -3.47131265 -0.298164155 -0.63408128 0.29410295 0.54061400 ## [35,] 0.61793000 0.438578669 -0.66813506 -0.23108089 0.02655948 ## [36,] 0.76938343 0.351903043 -0.66813506 -0.14355025 -1.30141468 ## [37,] 0.84511015 1.522023999 -0.70218883 -0.75626474 -0.83019804 ## [38,] -1.50241804 -2.248365748 -0.77029638 -1.54404051 -1.51560407 ## [39,] 0.84511015 0.741943362 -0.80435016 -0.49367282 -0.14479202 ## [40,] 0.61793000 0.525254296 -0.87245770 -0.84379538 -0.91587380 ## [41,] -0.29079059 -0.991569166 -0.87245770 -0.40614217 -0.14479202 ## [42,] 0.61793000 0.005200538 -0.90651148 -1.01885666 -1.17290106 ## [43,] 0.76938343 0.351903043 -0.94056525 -0.05601961 -0.27330565 ## [44,] -1.42669132 -1.901663242 -0.97461903 -0.58120346 -0.35898140 ## [45,] 0.76938343 -0.558191034 -1.04272658 -0.84379538 -0.87303592 ## [46,] 0.31502314 -2.681743880 -1.04272658 -0.58120346 -2.02965858 ## [47,] 0.61793000 -0.038137276 -1.07678035 -1.19391794 -0.91587380 ## [48,] 0.61793000 -0.428177594 -1.07678035 -1.98169371 -1.51560407 ## [49,] -1.04805775 0.178551790 -1.14488790 -1.19391794 -0.57317079 ## [50,] 0.23929642 -2.768419506 -1.24704922 -1.19391794 -0.87303592 ## FGP FTM FTA FTP X3PM ## [1,] 0.51360167 1.91747526 2.11077208 -0.74016734 -0.1080044 ## [2,] 0.46491905 1.77872886 1.89658922 -0.52332144 0.4920201 ## [3,] -0.07058980 0.80750405 0.55794635 0.57536445 0.2520103 ## [4,] 0.22150593 0.87687725 0.45085492 1.06688183 -0.4680191 ## [5,] -0.55741603 0.87687725 0.55794635 0.89340511 1.8120740 ## [6,] 0.14848200 0.94625045 0.66503778 0.67655921 0.1320054 ## [7,] -1.21463144 2.95807327 2.37850066 0.73438478 1.3320544 ## [8,] 0.65964954 -0.71870636 -0.45942223 -1.13048996 -1.4280583 ## [9,] 0.80569741 0.73813085 0.45085492 0.74884117 -0.4680191 ## [10,] -0.65478128 0.59938445 0.66503778 -0.33538832 -0.2280093 ## [11,] 0.41623642 1.22374326 1.14694921 0.01156511 -1.1880485 ## [12,] 0.24584725 0.39126485 0.34376349 0.11275987 -0.1080044 ## [13,] -0.04624849 -0.37184035 -0.13814794 -0.89918766 0.2520103 ## [14,] 0.87872134 -0.57995996 -0.45942223 -0.49440865 -1.0680436 ## [15,] 1.68198462 0.94625045 0.77212921 0.27178019 -1.3080534 ## [16,] -0.80082915 -0.64933316 -0.67360509 0.14167265 0.8520348 ## [17,] -0.77648783 1.70935566 1.57531493 0.05493429 -0.3480142 ## [18,] -0.36268554 -0.51058676 -0.51296795 -0.03180407 1.0920446 ## [19,] 0.05111675 0.04439885 -0.19169366 0.98014347 -1.3080534 ## [20,] 0.12414069 -0.78807956 -0.51296795 -1.18831553 -0.7080289 ## [21,] -0.41136816 0.25251845 0.07603492 0.60427724 -0.2280093 ## [22,] -0.80082915 -0.37184035 -0.40587652 0.01156511 0.8520348 ## [23,] -1.36067931 0.18314525 0.07603492 0.14167265 0.6120250 ## [24,] -0.36268554 -0.51058676 -0.62005938 0.69101560 1.0920446 ## [25,] 2.48524789 1.15437006 2.59268352 -3.21221059 -1.4280583 ## [26,] -0.31400292 0.66875765 0.50440063 0.19949823 0.3720152 ## [27,] -0.75214652 -1.06557236 -0.99487938 -0.33538832 1.3320544 ## [28,] -1.45804455 -0.09434755 -0.29878509 0.80666675 1.2120495 ## [29,] 1.90105642 0.11377205 -0.08460223 0.71992839 -1.4280583 ## [30,] -0.75214652 0.25251845 0.23667206 -0.16191160 0.2520103 ## [31,] -0.16795505 -1.41243836 -1.53033653 0.92231789 1.3320544 ## [32,] 0.02677544 0.04439885 -0.13814794 0.47416970 -0.2280093 ## [33,] 0.83003872 -0.16372075 0.29021777 -1.79548405 -1.4280583 ## [34,] -0.46005079 -1.13494556 -1.10197081 0.19949823 -1.0680436 ## [35,] -0.41136816 -0.99619916 -0.78069652 -0.71125455 -0.1080044 ## [36,] 2.36354134 -0.37184035 -0.24523937 -0.50886504 -1.4280583 ## [37,] 0.07545807 -0.09434755 0.29021777 -1.33287946 -0.2280093 ## [38,] -0.21663767 1.36248966 1.20049493 0.11275987 -0.8280338 ## [39,] -0.77648783 -1.20431876 -1.31615367 0.90786150 0.7320299 ## [40,] 0.05111675 -0.78807956 -0.78069652 0.19949823 0.4920201 ## [41,] -0.55741603 -0.99619916 -1.04842510 0.45971331 -0.2280093 ## [42,] 0.24584725 -1.20431876 -1.42324510 1.96317821 1.5720642 ## [43,] 0.34321249 -1.06557236 -0.94133367 -0.50886504 -1.3080534 ## [44,] -0.46005079 -0.99619916 -0.88778795 -0.49440865 -0.1080044 ## [45,] -0.07058980 -1.48181156 -1.63742796 1.38492248 1.3320544 ## [46,] 3.38587642 -0.44121355 0.55794635 -3.19775420 -1.4280583 ## [47,] -0.75214652 -1.34306516 -1.31615367 0.28623659 1.9320789 ## [48,] -1.26331406 0.39126485 -0.03105651 1.39937887 1.0920446 ## [49,] -1.28765537 0.04439885 0.12958063 -0.50886504 -0.8280338 ## [50,] -0.80082915 -0.92682596 -0.99487938 0.35851855 0.6120250 ## X3PA X3PP ORB DRB TRB ## [1,] 0.13036473 -0.15749098 -0.27213551 -0.34656760 -0.32874654 ## [2,] 0.69716790 0.02738974 -0.06117775 1.00809403 0.66053702 ## [3,] 0.41376631 0.07532177 -0.27213551 -0.23367913 -0.25264780 ## [4,] -0.53090563 0.13010124 -0.27213551 1.57253638 0.96493197 ## [5,] 1.64183984 0.43823576 -0.69405103 -0.06434643 -0.29069717 ## [6,] -0.05856966 0.56148957 -0.37761439 0.55654016 0.24199398 ## [7,] 1.02780308 0.51355754 -0.79952991 -0.85456572 -0.86143769 ## [8,] -1.47557758 -2.32812750 2.15387873 1.68542485 1.95421553 ## [9,] -0.43643844 0.16433841 -0.48309327 0.10498628 -0.13849970 ## [10,] -0.29473765 0.21227045 0.25525889 0.38720745 0.35614208 ## [11,] -1.23940959 -0.65050621 1.52100545 1.51609215 1.57372185 ## [12,] -0.20027045 0.25335505 -0.06117775 -0.62878878 -0.44289464 ## [13,] 0.31929912 0.07532177 1.09908993 1.12098250 1.15517880 ## [14,] -1.09770880 -0.32867682 -1.01048767 -1.02389842 -1.05168452 ## [15,] -1.47557758 0.60942161 0.88813217 0.78231709 0.85078386 ## [16,] 0.93333588 0.13694868 -0.58857215 -0.51590031 -0.55704274 ## [17,] -0.01133606 -0.33552426 -1.01048767 -0.91100995 -0.97558579 ## [18,] 1.21673747 0.17803328 -0.69405103 -1.13678689 -1.01363516 ## [19,] -1.38111039 -0.68474338 0.78265329 1.06453827 1.00298133 ## [20,] -0.62537283 -0.06847434 1.83744209 1.34675944 1.61177122 ## [21,] -0.05856966 -0.20542301 0.46621665 -0.06434643 0.12784588 ## [22,] 0.79163509 0.30813452 -0.48309327 -0.17723490 -0.29069717 ## [23,] 0.93333588 -0.01369487 -0.16665663 -0.34656760 -0.29069717 ## [24,] 0.88610229 0.47932037 -0.79952991 -0.96745418 -0.89948705 ## [25,] -1.52281118 -2.32812750 3.10318865 2.87075378 3.01959782 ## [26,] 0.27206552 0.34921912 -0.69405103 0.27431898 -0.10045033 ## [27,] 1.50013905 0.16433841 0.04430113 0.21787475 0.12784588 ## [28,] 1.35843826 0.13694868 -1.01048767 -1.08034265 -1.08973389 ## [29,] -1.52281118 4.51930632 1.31004769 1.51609215 1.53567248 ## [30,] 0.17759833 0.39030373 -0.69405103 -0.34656760 -0.48094401 ## [31,] 1.40567186 0.17803328 -0.90500879 -1.47545230 -1.31803010 ## [32,] 0.03589753 -0.20542301 -1.01048767 -1.13678689 -1.12778326 ## [33,] -1.52281118 -2.32812750 1.41552657 1.96764603 1.84006742 ## [34,] -1.05047520 -0.21911788 -0.79952991 -0.40301184 -0.59509211 ## [35,] -0.05856966 0.07532177 0.04430113 -0.17723490 -0.13849970 ## [36,] -1.52281118 1.09558941 1.94292097 1.06453827 1.42152438 ## [37,] -0.01133606 -0.22596532 -0.27213551 0.04854204 -0.06240096 ## [38,] -0.62537283 -0.59572674 -0.37761439 0.04854204 -0.13849970 ## [39,] 0.64993430 0.30128709 -0.69405103 -0.79812148 -0.78533895 ## [40,] 0.27206552 0.52725240 -0.69405103 -0.57234454 -0.63314148 ## [41,] -0.20027045 0.19172815 -0.69405103 -1.19323112 -1.05168452 ## [42,] 1.40567186 0.47247293 -0.58857215 -1.02389842 -0.89948705 ## [43,] -1.38111039 -0.61626904 1.62648433 0.04854204 0.62248766 ## [44,] -0.01133606 0.03423717 -0.27213551 -0.34656760 -0.29069717 ## [45,] 0.93333588 0.65735365 -0.79952991 -0.91100995 -0.93753642 ## [46,] -1.52281118 -2.32812750 1.20456881 0.78231709 0.96493197 ## [47,] 1.78354063 0.39030373 -0.16665663 0.04854204 -0.06240096 ## [48,] 0.83886869 0.46562550 -1.01048767 -1.08034265 -1.08973389 ## [49,] -0.71984002 -0.39030373 -0.90500879 -1.13678689 -1.08973389 ## [50,] 0.93333588 -0.10271151 -0.06117775 -1.08034265 -0.74728958 ## AST STL BLK TO PF ## [1,] 1.65224666 2.55823818 1.206464582 1.7904454 -0.29845679 ## [2,] 1.51614727 1.36725206 0.862742479 1.0596514 -1.39037189 ## [3,] 0.47271857 0.89085761 -0.168423831 0.3288573 -0.29845679 ## [4,] -0.66144306 -0.77652295 0.347159324 -0.9500323 -0.48044264 ## [5,] -0.52534367 -0.30012850 1.378325634 0.1461588 1.15743000 ## [6,] -0.47997720 0.41446317 0.175298273 1.0596514 -1.20838604 ## [7,] -0.52534367 0.17626595 -0.684006985 0.8769529 -0.29845679 ## [8,] -1.02437478 -0.77652295 1.893908788 -1.1327308 0.61147245 ## [9,] 3.24007294 3.98742152 -0.855868037 1.0596514 0.42948660 ## [10,] -0.20777841 -0.06193128 -0.340284882 1.0596514 0.97544415 ## [11,] -0.61607660 -0.53832572 0.690881427 -0.2192382 0.06551491 ## [12,] 0.56345150 -0.06193128 -0.512145934 -0.9500323 -1.57235774 ## [13,] -0.88827539 0.17626595 -0.512145934 -1.6808263 0.42948660 ## [14,] 1.38004787 -0.53832572 -0.855868037 0.3288573 -1.75434359 ## [15,] -0.84290892 -0.53832572 0.862742479 0.6942543 1.15743000 ## [16,] 0.88101675 -0.06193128 -0.684006985 0.1461588 -0.48044264 ## [17,] 1.38004787 1.36725206 -0.684006985 1.2423499 -0.11647094 ## [18,] -0.52534367 -0.06193128 -0.855868037 -1.4981278 -1.93632944 ## [19,] -0.70680953 -1.25291739 0.519020376 -0.5846352 0.42948660 ## [20,] -0.79754246 -0.53832572 -0.512145934 -0.2192382 0.42948660 ## [21,] 0.20051978 1.12905484 -0.512145934 1.2423499 0.06551491 ## [22,] 0.38198564 -0.30012850 -0.168423831 -0.5846352 0.79345830 ## [23,] 1.19858201 0.89085761 -0.168423831 2.7039380 0.24750076 ## [24,] -0.20777841 -0.53832572 -0.512145934 -0.0365397 -0.48044264 ## [25,] -1.11510771 -0.30012850 3.956241407 1.0596514 1.70338755 ## [26,] -0.11704548 -0.30012850 -0.512145934 0.6942543 0.42948660 ## [27,] -1.11510771 0.17626595 -0.512145934 -0.4019367 1.15743000 ## [28,] 0.24588624 -0.53832572 -0.684006985 -0.2192382 -1.93632944 ## [29,] -0.93364185 -1.72931184 2.237630892 1.0596514 1.52140170 ## [30,] -0.66144306 -0.77652295 -0.684006985 -0.7673338 1.15743000 ## [31,] -0.20777841 0.41446317 -0.512145934 -1.4981278 -1.02640019 ## [32,] 3.10397355 -0.06193128 -0.512145934 1.7904454 -0.84441434 ## [33,] -0.16241195 -1.49111462 1.893908788 -0.4019367 -0.29845679 ## [34,] -0.07167901 1.12905484 -0.512145934 0.5115558 0.42948660 ## [35,] -0.97900832 0.17626595 0.175298273 0.3288573 0.61147245 ## [36,] -0.16241195 -1.25291739 0.690881427 -0.9500323 -0.66242849 ## [37,] 0.65418443 1.12905484 -0.340284882 0.5115558 -1.02640019 ## [38,] -0.93364185 -0.53832572 -0.684006985 -0.0365397 2.43133095 ## [39,] -0.29851134 -0.06193128 -0.684006985 0.6942543 0.06551491 ## [40,] -0.29851134 -0.06193128 -0.512145934 -0.5846352 -0.29845679 ## [41,] 0.24588624 -1.25291739 -0.855868037 -0.7673338 0.24750076 ## [42,] -0.47997720 -0.53832572 -0.684006985 -1.3154293 -0.84441434 ## [43,] -0.88827539 -0.30012850 0.690881427 -1.6808263 0.24750076 ## [44,] -1.02437478 -0.06193128 0.003437221 -1.3154293 0.24750076 ## [45,] 0.10978685 -0.53832572 -0.855868037 -0.4019367 0.42948660 ## [46,] -0.97900832 -1.01472017 1.378325634 -0.4019367 1.70338755 ## [47,] -0.57071013 -0.30012850 0.003437221 -0.7673338 0.06551491 ## [48,] 1.15321554 0.17626595 -0.684006985 -0.4019367 -0.84441434 ## [49,] 0.51808503 0.89085761 -0.855868037 0.3288573 -1.75434359 ## [50,] 0.10978685 0.41446317 -0.855868037 -0.9500323 0.61147245
Heatmap 資料前處理：scale
nba.m <- melt(nba)
ggplot(nba.m, aes(variable, Name)) + #aes(x,y)
geom_tile(aes(fill = value),colour = "white")+ #geom_tile: 區塊著色
scale_fill_gradient(low = "white",high = "steelblue") #數值低：白色
Treemap
需要treemapify packages 
Treemap -資料處理
- 需要
treemapifypackages - 參考資料
- G20 Dataset
if (!require('treemapify')){
library(devtools) #install.packages("devtools") 沒安裝過記得先裝
install_github("wilkox/treemapify") #從GitHub安裝測試版Packages,需要安裝devtools
library(treemapify)
}
data(G20)#範例資料
head(G20)
## Region Country Trade.mil.USD Nom.GDP.mil.USD HDI ## 1 Africa South Africa 208000 384315 0.629 ## 2 North America United States 3969000 15684750 0.937 ## 3 North America Canada 962600 1819081 0.911 ## 4 North America Mexico 756800 1177116 0.775 ## 5 South America Brazil 494800 2395968 0.730 ## 6 South America Argentina 152690 474954 0.811 ## Population Economic.classification ## 1 53000000 Developing ## 2 316173000 Advanced ## 3 34088000 Advanced ## 4 112211789 Developing ## 5 201032714 Developing ## 6 40117096 Developing
Treemap -設定Treemap參數
#treemapify: 將資料轉為treemap所需格式
#area:面積來源(GDP)
#fill:著色來源(HDI)
#label:每個方塊分類依據(Country)
#group:方塊群組(Region)
treeMapCoordinates <- treemapify(data=G20, #data=資料來源(G20)
area = "Nom.GDP.mil.USD",fill = "HDI",
label = "Country",group = "Region")
head(treeMapCoordinates)
## fill label xmin xmax ymin ymax group ## 1 0.876 European Union 0.00000 38.66972 0.00000 58.99641 Europe ## 2 0.920 Germany 38.66972 63.32079 0.00000 19.17284 Europe ## 3 0.893 France 38.66972 63.32079 19.17284 33.88097 Europe ## 4 0.875 United Kingdom 38.66972 63.32079 33.88097 47.64081 Europe ## 5 0.881 Italy 38.66972 63.32079 47.64081 58.99641 Europe ## 6 0.937 United States 0.00000 53.16491 58.99641 100.00000 North America
Treemap -作圖1
ggplotify(treeMapCoordinates)
Treemap -作圖2
好像數字越大顏色越深比較合理？
ggplotify(treeMapCoordinates)+
scale_fill_gradient(low = "white",high = "steelblue") #指定高低顏色
Homework 6 -1
- Data from
Project Tycho® - University of Pittsburgh
- Advance the availability and use of public health data for science and policy making
- Data from all weekly notifiable disease reports for the US dating back to
1888 - Download @ Course Website
POLIO_Incidence.csv - 題目：請用圖表呈現1928-1969間，小兒麻痺在美國各州的發生率變化
- 注意：
1955年開始有小兒麻痺疫苗
Homework 6 -2
- 題目：請用圖表呈現1928-1969間，小兒麻痺在美國各州的發生率變化
- 預計會遇到的問題：
- 下載的資料，沒有資料是用
-表示，畫圖時必須注意（轉為NA） - 資料以每週/每州呈現，需依各州各年度加總，計算該年度的總發生率
- 資料屬於
寬版表格，必須改成長版表格處理 50個州與>20年的資料，如何呈現？
- 下載的資料，沒有資料是用
Homework 6 -3
- 題目：請用圖表呈現1928-1969間，小兒麻痺在美國各州的發生率變化
- 要求：
- 用
ggplot2package做圖（或其他衍伸的packages） - 呈現各州，各年，發生率的變化
- 用
- 圖形格式不限
- 5/16(一) 11:59pm 繳交
Homework 6 -4
- Title：1928-1969間，小兒麻痺在美國各州的發生率變化 (
5 pt) - 次標題1：資料前處理 (
20 pt)- 把資料讀進來 (
5 pt) - 將寬表格轉為長表格 (
5 pt) - 處理缺值 (
5 pt) - 計算年度發生率 (
5 pt)
- 把資料讀進來 (
- 次標題2：視覺畫呈現 (
80 pt)- 解釋如何選擇圖形種類 (
10 pt) - 程式碼 (
20 pt) - 圖形呈現 (
40 pt)，按照是否可以輕易看懂圖形給分 - 解釋圖形 (
10 pt)
- 解釋如何選擇圖形種類 (
Homework 6 -提示1
#讀csv資料
polio<-read.csv("POLIO_Incidence.csv",stringsAsFactors = F)
head(polio)
## YEAR WEEK ALABAMA ALASKA ARIZONA ARKANSAS CALIFORNIA COLORADO ## 1 1928 1 0 - 0 0 0.17 0.39 ## 2 1928 2 0 - 0 0 0.15 0.2 ## 3 1928 3 0.04 - 0 0 0.11 0 ## 4 1928 4 0 - 0.24 0.11 0.07 0.2 ## 5 1928 5 0 - 0.24 0 0.32 0 ## 6 1928 6 0 - 0 0 0.22 0.1 ## CONNECTICUT DELAWARE DISTRICT.OF.COLUMBIA FLORIDA GEORGIA HAWAII IDAHO ## 1 0 0 - 0 0.03 - 0 ## 2 0 0 - 0 0 - 0 ## 3 0.06 0 - 0 - - 0 ## 4 0.06 0 0 0 0 - 0 ## 5 0.13 0 0 0 0 - 0 ## 6 0 0 0 0 0 - - ## ILLINOIS INDIANA IOWA KANSAS KENTUCKY LOUISIANA MAINE MARYLAND ## 1 0.03 0.03 0.08 0 0 0 0 0.06 ## 2 0.01 0.03 - 0.22 0 0.05 0.13 0.06 ## 3 0.03 0.03 - 0 0 0 0 0 ## 4 0.05 0.12 0 0 0 0 0 0 ## 5 0.04 0 0.04 0 0 0 0.38 0.12 ## 6 0.03 0 0 0 0 0 0 0 ## MASSACHUSETTS MICHIGAN MINNESOTA MISSISSIPPI MISSOURI MONTANA NEBRASKA ## 1 0.14 0.04 0 0 0.03 0.18 0.07 ## 2 0.14 0.04 0.04 0 0.06 0 0.07 ## 3 0.07 0.02 0 0 0.03 0.18 0 ## 4 0.02 0.02 0 0 0.06 0 0 ## 5 0.02 0.04 0 0 0 0 0.15 ## 6 0.05 0.06 0 0 0 0 0.07 ## NEVADA NEW.HAMPSHIRE NEW.JERSEY NEW.MEXICO NEW.YORK NORTH.CAROLINA ## 1 - - 0.08 0 0.08 0 ## 2 - - 0.03 0 0.05 0.03 ## 3 - - 0 0 0.03 0 ## 4 - 0 0.03 0 0.06 0 ## 5 - 0 0.03 0.48 0.07 0 ## 6 - 0 0 0 0.03 0 ## NORTH.DAKOTA OHIO OKLAHOMA OREGON PENNSYLVANIA RHODE.ISLAND ## 1 - 0.02 0 0.64 0 0 ## 2 0.45 - 0.04 0.43 0.03 0 ## 3 0 0.06 0 1.07 0.02 0 ## 4 0.15 0 0.09 0.53 0.02 0 ## 5 0 0.03 0 0.32 0 0 ## 6 0 0.05 0.04 0.21 0.04 0 ## SOUTH.CAROLINA SOUTH.DAKOTA TENNESSEE TEXAS UTAH VERMONT VIRGINIA ## 1 0.06 0 0.04 0.05 0 0 - ## 2 0.06 0 0.04 0.04 0 0 - ## 3 0.35 0 0 0 0 0 - ## 4 0.23 0 0.04 0.05 0 0 - ## 5 0.17 0.15 0 0.05 0 0 - ## 6 0.06 0.29 0.04 0 0.2 0 0.04 ## WASHINGTON WEST.VIRGINIA WISCONSIN WYOMING ## 1 0.26 0.06 0.03 0 ## 2 0.39 0.24 0.03 0 ## 3 0.13 0.12 0.03 0 ## 4 0.06 0.12 0 0 ## 5 0.13 0.06 0.03 0 ## 6 0.06 0 0.14 0
Homework 6 -提示2
#將寬表格轉為長表格，以年(YEAR)/週(WEEK)為基準，各州名column打散變長
polio.m<-melt(polio,id.vars = c('YEAR','WEEK'))
head(polio.m)
## YEAR WEEK variable value ## 1 1928 1 ALABAMA 0 ## 2 1928 2 ALABAMA 0 ## 3 1928 3 ALABAMA 0.04 ## 4 1928 4 ALABAMA 0 ## 5 1928 5 ALABAMA 0 ## 6 1928 6 ALABAMA 0
Homework 6 -提示3
polio.m[polio.m$value=="-",]$value<-NA #處理缺值,將"-"轉為NA
polio.m$value<-as.numeric(polio.m$value) #將value欄位轉為數字
polio.sumYear<- #各州各年度加總，計算該年度的總發生率
aggregate(value~YEAR+variable,data=polio.m,FUN=sum,na.rm=F)
head(polio.sumYear)
## YEAR variable value ## 1 1928 ALABAMA 2.39 ## 2 1929 ALABAMA 2.25 ## 3 1930 ALABAMA 2.57 ## 4 1931 ALABAMA 2.07 ## 5 1932 ALABAMA 1.38 ## 6 1933 ALABAMA 1.12
Homework 6 -錯誤示範，不要這樣畫！
ggplot(polio.sumYear)+ #資料為polio.sumYear
geom_line(aes(x=YEAR,y=value,color=variable))+ #geom_line:畫折線圖
geom_vline(xintercept = 1955,colour="black", linetype = "longdash")#疫苗
Error bar 誤差線
- 終於要扯一點所謂的統計
- 通常使用在bar chart, line chart
- 比較多組資料的平均值高低時，務必加上Error bar 誤差線
- 誤差線計算
- Standard deviation (SD) 標準差：呈現資料本質時使用
- Standard error (SE) 標準誤差：呈現預估平均值的可能誤差時使用
- Confidence interval (CI) 信賴區間：呈現預估平均值的信心時使用
Bar Chart without Error Bar in ggplot2
library(datasets)
airquality$Month<-as.factor(airquality$Month) #將Month轉為因子變項
airquality.mean<-aggregate(Ozone~Month,airquality,mean) #計算每月Ozone平均mean
ggplot()+geom_bar(data=airquality.mean,aes(x=Month,y=Ozone),
stat = "identity") #stat = "identity" 直接畫數字
Bar Chart with Error Bar in ggplot2
airquality.sd<-aggregate(Ozone~Month,airquality,sd) #計算每月Ozone標準差sd
airquality.eb<-merge(airquality.mean,airquality.sd,by="Month")
ggplot(data=airquality.eb)+ #資料airquality.eb
geom_bar(aes(x=Month,y=Ozone.x),stat = "identity")+
geom_errorbar( #ymin低點, ymax高點, Ozone.x=mean, Ozone.y=sd標準差
aes(x=Month,ymin=Ozone.x-Ozone.y,ymax=Ozone.x+Ozone.y), width=.1)
Clustering
汽車基本資料
mtcars.mx<-as.matrix(mtcars) mtcars.mxs<-scale(mtcars.mx) #[, 1] mpg Miles/(US) gallon #[, 2] cyl Number of cylinders 氣缸數 #[, 3] disp Displacement (cu.in.) 排氣量 #[, 4] hp Gross horsepower 馬力 #[, 5] drat Rear axle ratio 後輪軸比 #[, 6] wt Weight (1000 lbs) #[, 7] qsec 1/4 mile time #[, 8] vs V/S #[, 9] am Transmission (0 = automatic, 1 = manual) #[,10] gear Number of forward gears 前進檔 #[,11] carb Number of carburetors 化油器 head(mtcars.mxs,3)
## mpg cyl disp hp drat ## Mazda RX4 0.1508848 -0.1049878 -0.5706198 -0.5350928 0.5675137 ## Mazda RX4 Wag 0.1508848 -0.1049878 -0.5706198 -0.5350928 0.5675137 ## Datsun 710 0.4495434 -1.2248578 -0.9901821 -0.7830405 0.4739996 ## wt qsec vs am gear ## Mazda RX4 -0.6103996 -0.7771651 -0.8680278 1.189901 0.4235542 ## Mazda RX4 Wag -0.3497853 -0.4637808 -0.8680278 1.189901 0.4235542 ## Datsun 710 -0.9170046 0.4260068 1.1160357 1.189901 0.4235542 ## carb ## Mazda RX4 0.7352031 ## Mazda RX4 Wag 0.7352031 ## Datsun 710 -1.1221521
各汽車/參數間的相似性？ -heatmap()
par(mar=rep(0.2,4),mfrow=c(1,1)) heatmap(mtcars.mxs)
如何找到相似的物件/事件？
Clustering organizes things that are close into groups
- How do we define close?
- How do we group things?
- How do we visualize the grouping?
- How do we interpret the grouping?
Hierarchical clustering
- An agglomerative approach
- Find closest two things
- Put them together
- Find next closest
- Requires
- A defined distance
- A merging approach
- Produces
- A tree showing how close things are to each other
Hierarchical clustering
- An agglomerative approach
- Find closest two things
- Put them together
- Find next closest
- Requires
A defined distance- A merging approach
- Produces
- A tree showing how close things are to each other
How do we define close? distance
- Most important step
- Garbage in -> garbage out
- Distance or similarity
- Continuous - euclidean distance
- Continuous - correlation similarity
- Binary - manhattan distance
- Pick a distance/similarity that makes sense for your problem
Example distances - Euclidean
\[\sqrt{(A_1-A_2)^2 + (B_1-B_2)^2 + \ldots + (Z_1-Z_2)^2}\]
Example distances - Manhattan
\[|A_1-A_2| + |B_1-B_2| + \ldots + |Z_1-Z_2|\]
Green line: Euclidean, Blue line: Manhattan
Hierarchical clustering
- An agglomerative approach
- Find closest two things
- Put them together
- Find next closest
- Requires
- A defined distance
A merging approach
- Produces
- A tree showing how close things are to each other
Merging apporach
- Agglomerative 聚合
- Single-linkage：取最小值
- Complete-linkage：取最大值
- Average-linkage：取平均值
Hierarchical clustering - hp vs. mpg
Hierarchical clustering - #1
Hierarchical clustering - #2
Hierarchical clustering - #3
Hierarchical clustering
- An agglomerative approach
- Find closest two things
- Put them together
- Find next closest
Requires- A defined distance
- A merging approach
- Produces
- A tree showing how close things are to each other
Hierarchical Clustering -dist()
用dist()函數計算距離，使用method=""設定計算距離的依據
d<-dist(mtcars.mxs) #預設為euclidean d
## Mazda RX4 Mazda RX4 Wag Datsun 710 Hornet 4 Drive ## Mazda RX4 Wag 0.4075899 ## Datsun 710 3.2430644 3.1763654 ## Hornet 4 Drive 4.4013651 4.2633265 3.4371367 ## Hornet Sportabout 3.8803542 3.8196912 5.0032747 3.0421632 ## Valiant 4.8437395 4.6756447 3.8681280 0.9936969 ## Duster 360 4.1895788 4.1749365 5.8959064 4.3395668 ## Merc 240D 3.9972560 3.8208496 2.5014249 2.5336229 ## Merc 230 4.9177375 4.6700230 3.3122031 3.2698916 ## Merc 280 3.1377712 2.9882339 3.2950024 2.9859746 ## Merc 280C 3.2928005 3.1170530 3.3443599 2.9705073 ## Merc 450SE 3.8563035 3.7329721 5.1667877 3.2468885 ## Merc 450SL 3.7264672 3.6140741 5.0139378 3.0963299 ## Merc 450SLC 3.8587627 3.7280140 5.0836872 3.1350053 ## Cadillac Fleetwood 5.4495167 5.2848094 6.7701575 4.6845022 ## Lincoln Continental 5.4799639 5.3127593 6.8196686 4.7868961 ## Chrysler Imperial 5.0972757 4.9355861 6.5250751 4.6034009 ## Fiat 128 4.0243306 3.9407293 1.7832069 4.1853934 ## Honda Civic 4.0533412 4.0507443 2.6458745 5.2450434 ## Toyota Corolla 4.3445000 4.2722835 2.2120337 4.5513874 ## Toyota Corona 4.3303364 4.2137101 2.5743286 2.1359358 ## Dodge Challenger 4.1089579 4.0529524 5.1794615 3.1033485 ## AMC Javelin 3.7602309 3.6846550 4.8499144 2.9346504 ## Camaro Z28 4.1191859 4.1051443 5.9277646 4.6740373 ## Pontiac Firebird 4.1721471 4.0882070 5.2718706 3.1815173 ## Fiat X1-9 3.6110861 3.5658305 1.0646650 3.9829642 ## Porsche 914-2 2.5948592 2.6591243 2.9668981 5.3633226 ## Lotus Europa 3.5593956 3.6429111 2.3504814 4.8654619 ## Ford Pantera L 3.6239136 3.7004541 5.6724603 6.2182516 ## Ferrari Dino 2.2173337 2.3107383 4.6711840 5.7255126 ## Maserati Bora 4.9757567 5.0070559 7.2893098 7.4540115 ## Volvo 142E 2.9056273 2.7880036 0.9799181 3.5836208 ## Hornet Sportabout Valiant Duster 360 Merc 240D ## Mazda RX4 Wag ## Datsun 710 ## Hornet 4 Drive ## Hornet Sportabout ## Valiant 3.3988179 ## Duster 360 1.8907332 4.5959496 ## Merc 240D 4.6074904 2.9114013 5.6208325 ## Merc 230 5.3601882 3.4090956 6.3074270 1.7677287 ## Merc 280 3.7603055 3.3860393 4.1159325 2.3467260 ## Merc 280C 3.8404534 3.2902323 4.2017096 2.3314789 ## Merc 450SE 1.2157212 3.3739087 1.7195474 4.6100696 ## Merc 450SL 1.0581618 3.2662012 1.7483591 4.4789673 ## Merc 450SLC 1.2772271 3.2103732 1.8280213 4.5289442 ## Cadillac Fleetwood 2.8840440 4.6250214 2.4964362 6.0571351 ## Lincoln Continental 2.9684612 4.7409039 2.4967056 6.1200901 ## Chrysler Imperial 2.6262007 4.7149888 2.1314298 5.8475038 ## Fiat 128 5.8776367 4.7310845 6.9265472 2.8477338 ## Honda Civic 6.5054903 5.8852758 7.2973276 3.7432868 ## Toyota Corolla 6.2330226 5.1096664 7.2823316 3.1877164 ## Toyota Corona 4.4095161 2.5379207 5.4586640 1.8187717 ## Dodge Challenger 1.0370480 3.2050198 2.1565615 4.7681748 ## AMC Javelin 0.8360206 3.1377397 2.0925400 4.4434196 ## Camaro Z28 2.3538211 5.0148655 1.0554323 5.7074187 ## Pontiac Firebird 0.5475333 3.5076094 1.9842791 4.7856750 ## Fiat X1-9 5.6028144 4.4964851 6.5754940 2.7365898 ## Porsche 914-2 5.5333206 5.9048663 6.1678160 4.0696390 ## Lotus Europa 5.8906362 5.4091213 6.5673285 3.6797302 ## Ford Pantera L 4.5704575 6.6597531 3.9756842 6.3426475 ## Ferrari Dino 4.8737371 6.0393960 4.5054188 5.2004290 ## Maserati Bora 5.7962447 7.6982401 4.5080940 7.6028670 ## Volvo 142E 4.9104611 4.0221723 5.5902795 2.4866260 ## Merc 230 Merc 280 Merc 280C Merc 450SE Merc 450SL ## Mazda RX4 Wag ## Datsun 710 ## Hornet 4 Drive ## Hornet Sportabout ## Valiant ## Duster 360 ## Merc 240D ## Merc 230 ## Merc 280 3.1736664 ## Merc 280C 2.9644001 0.4082884 ## Merc 450SE 5.2829002 3.5036558 3.5446708 ## Merc 450SL 5.1385834 3.4252318 3.4663403 0.3944266 ## Merc 450SLC 5.0939035 3.4613499 3.4571735 0.4901305 0.4172832 ## Cadillac Fleetwood 6.4719931 4.8481443 4.8076108 2.3752167 2.6191633 ## Lincoln Continental 6.5342344 4.8652211 4.8310582 2.4147746 2.6820009 ## Chrysler Imperial 6.3195516 4.5331791 4.5497518 2.1301591 2.3833766 ## Fiat 128 3.4760961 4.1044898 4.1942047 6.1027421 5.9176565 ## Honda Civic 4.2793565 4.3521695 4.4596794 6.7429222 6.5608536 ## Toyota Corolla 3.6385061 4.4495050 4.5273217 6.4894198 6.2849281 ## Toyota Corona 2.3602221 3.0091888 2.9591531 4.5230838 4.3467458 ## Dodge Challenger 5.5840526 3.9899083 4.0420607 1.2054395 1.1528213 ## AMC Javelin 5.1708093 3.5713821 3.6040168 1.0549265 0.9430857 ## Camaro Z28 6.3746076 4.0282873 4.1261450 2.1735238 2.2625903 ## Pontiac Firebird 5.5292039 3.9725287 4.0518437 1.3039453 1.2653565 ## Fiat X1-9 3.4679554 3.7810906 3.8551580 5.8249673 5.6428137 ## Porsche 914-2 4.9107991 4.2059850 4.3568869 5.7510348 5.6099124 ## Lotus Europa 4.6690572 4.1265650 4.3109976 6.1480650 5.9587741 ## Ford Pantera L 7.0037774 4.7638360 4.9017138 4.6618197 4.6520853 ## Ferrari Dino 6.0347907 3.8958003 4.0539793 4.6304461 4.5549676 ## Maserati Bora 8.1527622 5.7612264 5.8672946 5.4444617 5.4646796 ## Volvo 142E 3.1932948 2.7801612 2.8200779 4.9479927 4.8294785 ## Merc 450SLC Cadillac Fleetwood Lincoln Continental ## Mazda RX4 Wag ## Datsun 710 ## Hornet 4 Drive ## Hornet Sportabout ## Valiant ## Duster 360 ## Merc 240D ## Merc 230 ## Merc 280 ## Merc 280C ## Merc 450SE ## Merc 450SL ## Merc 450SLC ## Cadillac Fleetwood 2.4458852 ## Lincoln Continental 2.5174149 0.2956825 ## Chrysler Imperial 2.3303195 1.0635310 0.9080748 ## Fiat 128 6.0522758 7.7973439 7.8458703 ## Honda Civic 6.6876038 8.3928547 8.4234897 ## Toyota Corolla 6.4199329 8.2005281 8.2527181 ## Toyota Corona 4.3683285 6.1484614 6.2160567 ## Dodge Challenger 1.2246720 2.8372165 2.9549058 ## AMC Javelin 0.9626504 2.8988638 2.9910214 ## Camaro Z28 2.3169202 2.8150659 2.7412463 ## Pontiac Firebird 1.4562704 2.5701272 2.6555931 ## Fiat X1-9 5.7474798 7.5268299 7.5797064 ## Porsche 914-2 5.7482820 7.3428177 7.3625764 ## Lotus Europa 6.1321085 7.8314188 7.8778088 ## Ford Pantera L 4.7410691 5.2908702 5.2360533 ## Ferrari Dino 4.6718041 5.8052611 5.8069129 ## Maserati Bora 5.5262308 5.6040962 5.5359080 ## Volvo 142E 4.8806503 6.4042902 6.4299677 ## Chrysler Imperial Fiat 128 Honda Civic Toyota Corolla ## Mazda RX4 Wag ## Datsun 710 ## Hornet 4 Drive ## Hornet Sportabout ## Valiant ## Duster 360 ## Merc 240D ## Merc 230 ## Merc 280 ## Merc 280C ## Merc 450SE ## Merc 450SL ## Merc 450SLC ## Cadillac Fleetwood ## Lincoln Continental ## Chrysler Imperial ## Fiat 128 7.4347239 ## Honda Civic 7.9702830 1.9243376 ## Toyota Corolla 7.8280569 0.5757917 1.7799297 ## Toyota Corona 5.9697480 3.1795988 3.9646286 3.4386884 ## Dodge Challenger 2.8683778 6.1897572 6.9208270 6.5812246 ## AMC Javelin 2.8183456 5.8508670 6.4507155 6.2193563 ## Camaro Z28 2.2659922 6.9503062 7.1027162 7.2970631 ## Pontiac Firebird 2.3043685 6.1149641 6.7946533 6.4857014 ## Fiat X1-9 7.2243403 0.9440123 1.8356814 1.2631917 ## Porsche 914-2 6.9369982 3.2195133 2.9932093 3.4109616 ## Lotus Europa 7.4655971 2.3907048 2.8622875 2.5923660 ## Ford Pantera L 4.8165342 6.6166138 6.4835328 6.9120796 ## Ferrari Dino 5.4553770 5.4662206 5.4859770 5.7728984 ## Maserati Bora 5.2173124 8.1807755 8.1867266 8.4801671 ## Volvo 142E 6.1099484 2.1944946 2.6127269 2.6006079 ## Toyota Corona Dodge Challenger AMC Javelin Camaro Z28 ## Mazda RX4 Wag ## Datsun 710 ## Hornet 4 Drive ## Hornet Sportabout ## Valiant ## Duster 360 ## Merc 240D ## Merc 230 ## Merc 280 ## Merc 280C ## Merc 450SE ## Merc 450SL ## Merc 450SLC ## Cadillac Fleetwood ## Lincoln Continental ## Chrysler Imperial ## Fiat 128 ## Honda Civic ## Toyota Corolla ## Toyota Corona ## Dodge Challenger 4.5624114 ## AMC Javelin 4.1915369 0.7827694 ## Camaro Z28 5.5640650 2.7782606 2.4813171 ## Pontiac Firebird 4.6855121 1.1942533 1.1771569 2.4529311 ## Fiat X1-9 2.8771692 5.8525045 5.4949181 6.5789332 ## Porsche 914-2 4.6534714 5.8698053 5.4885985 6.0073280 ## Lotus Europa 4.2445533 6.1425433 5.9214212 6.6478423 ## Ford Pantera L 6.7110287 5.0078711 4.7275036 3.6306118 ## Ferrari Dino 5.8353128 5.0080706 4.8308278 4.5053590 ## Maserati Bora 8.0606070 6.0178217 5.9396759 4.4569171 ## Volvo 142E 2.7534994 5.1510061 4.7542900 5.5099681 ## Pontiac Firebird Fiat X1-9 Porsche 914-2 Lotus Europa ## Mazda RX4 Wag ## Datsun 710 ## Hornet 4 Drive ## Hornet Sportabout ## Valiant ## Duster 360 ## Merc 240D ## Merc 230 ## Merc 280 ## Merc 280C ## Merc 450SE ## Merc 450SL ## Merc 450SLC ## Cadillac Fleetwood ## Lincoln Continental ## Chrysler Imperial ## Fiat 128 ## Honda Civic ## Toyota Corolla ## Toyota Corona ## Dodge Challenger ## AMC Javelin ## Camaro Z28 ## Pontiac Firebird ## Fiat X1-9 5.8831504 ## Porsche 914-2 5.8049597 2.9043943 ## Lotus Europa 6.1638574 2.1786546 2.5613776 ## Ford Pantera L 4.7026976 6.2258629 4.6929233 5.5540990 ## Ferrari Dino 5.0961648 5.1088276 3.6305579 4.2187875 ## Maserati Bora 5.8678663 7.8702812 6.5745699 6.9847187 ## Volvo 142E 5.1557398 1.6207836 2.8881825 2.6646220 ## Ford Pantera L Ferrari Dino Maserati Bora ## Mazda RX4 Wag ## Datsun 710 ## Hornet 4 Drive ## Hornet Sportabout ## Valiant ## Duster 360 ## Merc 240D ## Merc 230 ## Merc 280 ## Merc 280C ## Merc 450SE ## Merc 450SL ## Merc 450SLC ## Cadillac Fleetwood ## Lincoln Continental ## Chrysler Imperial ## Fiat 128 ## Honda Civic ## Toyota Corolla ## Toyota Corona ## Dodge Challenger ## AMC Javelin ## Camaro Z28 ## Pontiac Firebird ## Fiat X1-9 ## Porsche 914-2 ## Lotus Europa ## Ford Pantera L ## Ferrari Dino 3.0648409 ## Maserati Bora 3.0287549 3.3719604 ## Volvo 142E 5.2160045 4.2489749 6.7446456
Hierarchical Clustering -dist()
用dist()函數計算距離，使用method=""設定計算距離的依據，可用方法包括： "euclidean", "maximum", "manhattan", "canberra", "binary" or "minkowski"
d<-dist(mtcars.mxs, method="manhattan") #計算manhattan距離 d
## Mazda RX4 Mazda RX4 Wag Datsun 710 Hornet 4 Drive ## Mazda RX4 Wag 0.5739986 ## Datsun 710 7.5307482 7.4779782 ## Hornet 4 Drive 11.8673022 11.2933035 8.9891038 ## Hornet Sportabout 11.2150297 10.6410310 15.4555075 7.6572038 ## Valiant 13.3741549 12.8001562 10.4828422 2.1721112 ## Duster 360 11.7820302 11.8348003 19.1257503 11.5518804 ## Merc 240D 10.6740916 10.1000930 5.6192926 6.6700449 ## Merc 230 11.2015603 10.6275616 6.2969217 8.0647933 ## Merc 280 6.4428451 5.8688464 7.9460836 6.9357072 ## Merc 280C 7.0109040 6.4369054 8.1671813 6.8322283 ## Merc 450SE 11.3772351 10.8032364 16.4306424 8.3704992 ## Merc 450SL 10.9923430 10.4183444 15.8219044 7.7617612 ## Merc 450SLC 11.6157249 11.0417262 15.9975943 7.9374512 ## Cadillac Fleetwood 15.4937110 14.9197124 21.1362018 13.0760587 ## Lincoln Continental 15.5001133 14.9261147 21.3216809 13.2615377 ## Chrysler Imperial 14.1093081 13.5353095 20.3785676 12.8795090 ## Fiat 128 10.6008480 10.5480780 3.2571280 11.3172712 ## Honda Civic 11.5342698 11.4814998 5.5295172 14.5186211 ## Toyota Corolla 11.8011460 11.7483760 4.4574260 12.5175692 ## Toyota Corona 11.4343094 11.3815393 4.9432809 4.6837839 ## Dodge Challenger 11.7697013 11.3635872 16.1780636 8.1179205 ## AMC Javelin 11.1308717 10.5568731 15.0579652 7.2596615 ## Camaro Z28 11.4112990 11.4640690 18.7550190 13.1262424 ## Pontiac Firebird 12.0164341 11.4424355 16.2233351 8.1631919 ## Fiat X1-9 9.7040821 9.6513120 2.3603620 11.0248892 ## Porsche 914-2 6.7566501 7.0620336 6.9555078 15.7461264 ## Lotus Europa 9.4453466 9.5268842 5.5626132 13.7565767 ## Ford Pantera L 9.3826778 9.4354478 16.9134260 18.5443344 ## Ferrari Dino 5.0925824 5.3599760 12.1942473 15.6059216 ## Maserati Bora 13.0516657 13.1044357 20.3953857 20.7747378 ## Volvo 142E 6.4916534 6.1118380 2.1516587 9.0594209 ## Hornet Sportabout Valiant Duster 360 Merc 240D ## Mazda RX4 Wag ## Datsun 710 ## Hornet 4 Drive ## Hornet Sportabout ## Valiant 8.4734316 ## Duster 360 3.8946766 12.1281218 ## Merc 240D 12.8271725 7.5370146 16.4974152 ## Merc 230 14.2219209 8.6855324 17.8921636 2.8883172 ## Merc 280 10.2477369 7.3853351 11.4415061 5.9162388 ## Merc 280C 10.6498744 6.9168290 11.5449850 5.8127599 ## Merc 450SE 2.7591785 8.9093349 4.2408037 13.8023074 ## Merc 450SL 2.3742864 8.3005969 4.1545702 13.1935693 ## Merc 450SLC 2.9976683 8.4762869 4.0810820 13.3692593 ## Cadillac Fleetwood 6.7551549 13.0912154 5.5724155 18.5078668 ## Lincoln Continental 6.7615572 13.5385340 5.2871147 18.6933458 ## Chrysler Imperial 5.6699971 13.4557504 3.6663034 17.7502326 ## Fiat 128 18.7126355 12.7774326 22.3828783 6.5953360 ## Honda Civic 19.6460573 16.0123594 23.3163001 8.4753448 ## Toyota Corolla 19.9129335 13.4964618 23.5831763 7.2851949 ## Toyota Corona 12.0791483 5.5395613 15.7493910 3.9460278 ## Dodge Challenger 2.1295683 7.4971814 4.6309404 13.5497286 ## AMC Javelin 1.5589925 7.8870037 4.2922189 12.4296302 ## Camaro Z28 5.6304087 13.7024837 1.7357321 16.2763065 ## Pontiac Firebird 0.9673259 9.1044605 4.5962782 13.5950001 ## Fiat X1-9 17.8158695 12.5186275 21.4861123 6.3365310 ## Porsche 914-2 15.2265911 17.2398647 18.5386803 10.5487891 ## Lotus Europa 17.1176574 15.3961666 20.6535926 9.1134753 ## Ford Pantera L 11.4922713 19.6213640 8.3610834 18.9325509 ## Ferrari Dino 12.6261833 16.6813785 12.4992614 14.4599283 ## Maserati Bora 14.0696176 21.3509791 10.4072310 21.7751397 ## Volvo 142E 14.2763955 10.6698404 17.9466382 5.3826778 ## Merc 230 Merc 280 Merc 280C Merc 450SE Merc 450SL ## Mazda RX4 Wag ## Datsun 710 ## Hornet 4 Drive ## Hornet Sportabout ## Valiant ## Duster 360 ## Merc 240D ## Merc 230 ## Merc 280 6.4506575 ## Merc 280C 6.3471786 0.5680590 ## Merc 450SE 15.1970558 9.9846350 10.0881139 ## Merc 450SL 14.5883177 9.3758970 9.4793759 0.6087380 ## Merc 450SLC 14.7640077 9.5515870 9.6550658 0.8312596 0.6233818 ## Cadillac Fleetwood 19.9026152 13.4519577 13.5554366 5.3547127 5.7396048 ## Lincoln Continental 20.0880943 13.6374368 13.7409156 5.3611150 5.7460071 ## Chrysler Imperial 19.1449810 12.6943235 12.7978023 4.5688000 5.1551534 ## Fiat 128 8.3296726 10.9413721 10.8378933 19.6877704 19.0790324 ## Honda Civic 10.3263627 11.8747939 12.1966223 20.6211922 20.0124542 ## Toyota Corolla 9.0487018 12.1416701 12.0381913 20.8880684 20.2793304 ## Toyota Corona 5.1152086 7.8415557 7.7380769 13.0542832 12.4455451 ## Dodge Challenger 14.9444770 10.9702930 11.0737719 2.9849858 2.8987524 ## AMC Javelin 13.8243786 9.8604148 9.9638937 2.3378753 2.2516419 ## Camaro Z28 17.5214324 11.0707749 11.1742537 5.2632766 5.4018868 ## Pontiac Firebird 14.9897485 11.0155645 11.5836235 2.6032544 2.4534262 ## Fiat X1-9 8.0708676 10.0446062 9.9411273 18.7910044 18.1822664 ## Porsche 914-2 11.5538680 12.8560687 13.4241277 16.6270333 16.2421412 ## Lotus Europa 10.5629575 11.3400927 11.9081516 18.5180996 18.1332075 ## Ford Pantera L 19.4260889 13.5273205 13.6307994 11.9588896 11.8726562 ## Ferrari Dino 15.7454824 10.4182126 10.9862716 12.7883887 12.4034966 ## Maserati Bora 23.1698881 16.7192306 16.8227095 13.4636610 13.3774276 ## Volvo 142E 5.7401268 6.5051321 6.7374221 15.2515303 14.6427923 ## Merc 450SLC Cadillac Fleetwood Lincoln Continental ## Mazda RX4 Wag ## Datsun 710 ## Hornet 4 Drive ## Hornet Sportabout ## Valiant ## Duster 360 ## Merc 240D ## Merc 230 ## Merc 280 ## Merc 280C ## Merc 450SE ## Merc 450SL ## Merc 450SLC ## Cadillac Fleetwood 5.1386075 ## Lincoln Continental 5.3240866 0.6409627 ## Chrysler Imperial 4.9794635 2.3078438 1.8283598 ## Fiat 128 19.2547223 24.3933298 24.5788089 ## Honda Civic 20.1881441 25.3267516 25.5122307 ## Toyota Corolla 20.4550203 25.5936278 25.7791069 ## Toyota Corona 12.6212351 17.7598426 17.9453217 ## Dodge Challenger 2.9248170 6.8363791 7.1046208 ## AMC Javelin 2.1781536 6.8393128 6.8457151 ## Camaro Z28 5.2261969 6.4244156 6.1391148 ## Pontiac Firebird 2.9746064 5.9537504 5.9601527 ## Fiat X1-9 18.3579564 23.4965639 23.6820429 ## Porsche 914-2 16.8655230 21.9817460 21.9881482 ## Lotus Europa 18.7565894 23.8728123 23.8792146 ## Ford Pantera L 11.9982737 13.9334989 13.6481981 ## Ferrari Dino 13.0268785 16.9048646 16.9112669 ## Maserati Bora 13.3039393 15.9796465 15.6943457 ## Volvo 142E 14.8184823 19.9570898 20.1425688 ## Chrysler Imperial Fiat 128 Honda Civic ## Mazda RX4 Wag ## Datsun 710 ## Hornet 4 Drive ## Hornet Sportabout ## Valiant ## Duster 360 ## Merc 240D ## Merc 230 ## Merc 280 ## Merc 280C ## Merc 450SE ## Merc 450SL ## Merc 450SLC ## Cadillac Fleetwood ## Lincoln Continental ## Chrysler Imperial ## Fiat 128 23.6356956 ## Honda Civic 24.5691174 3.8986126 ## Toyota Corolla 24.8359936 1.2002980 3.7515780 ## Toyota Corona 17.0022084 7.2378713 10.4727981 ## Dodge Challenger 6.5741454 19.4351916 20.3686134 ## AMC Javelin 5.7541551 18.3150932 19.2485150 ## Camaro Z28 4.7753351 22.0121470 22.9455688 ## Pontiac Firebird 5.1304321 19.4804631 20.4138849 ## Fiat X1-9 22.7389296 1.4384349 3.4937318 ## Porsche 914-2 20.5973431 7.9867841 7.4883665 ## Lotus Europa 22.4884094 5.8442836 5.5819457 ## Ford Pantera L 11.8198383 19.3102243 19.7199672 ## Ferrari Dino 15.5204617 15.4513753 16.3847971 ## Maserati Bora 13.8659859 23.6525137 24.5859355 ## Volvo 142E 19.1994555 4.5484570 5.4592002 ## Toyota Corolla Toyota Corona Dodge Challenger ## Mazda RX4 Wag ## Datsun 710 ## Hornet 4 Drive ## Hornet Sportabout ## Valiant ## Duster 360 ## Merc 240D ## Merc 230 ## Merc 280 ## Merc 280C ## Merc 450SE ## Merc 450SL ## Merc 450SLC ## Cadillac Fleetwood ## Lincoln Continental ## Chrysler Imperial ## Fiat 128 ## Honda Civic ## Toyota Corolla ## Toyota Corona 7.9569005 ## Dodge Challenger 20.6354896 12.8017044 ## AMC Javelin 19.5153912 11.6816060 1.2196513 ## Camaro Z28 23.2124450 15.4908767 6.2053024 ## Pontiac Firebird 20.6807611 12.8469759 2.6715321 ## Fiat X1-9 2.0970640 6.9790663 18.5384257 ## Porsche 914-2 8.5407612 11.7035309 15.7812627 ## Lotus Europa 6.2985093 10.0899677 17.7059060 ## Ford Pantera L 19.9868434 20.8169872 12.3463775 ## Ferrari Dino 16.6516733 15.5367238 13.9101127 ## Maserati Bora 24.8528117 23.7378623 14.1281269 ## Volvo 142E 5.6365381 6.0552198 14.9989516 ## AMC Javelin Camaro Z28 Pontiac Firebird Fiat X1-9 ## Mazda RX4 Wag ## Datsun 710 ## Hornet 4 Drive ## Hornet Sportabout ## Valiant ## Duster 360 ## Merc 240D ## Merc 230 ## Merc 280 ## Merc 280C ## Merc 450SE ## Merc 450SL ## Merc 450SLC ## Cadillac Fleetwood ## Lincoln Continental ## Chrysler Imperial ## Fiat 128 ## Honda Civic ## Toyota Corolla ## Toyota Corona ## Dodge Challenger ## AMC Javelin ## Camaro Z28 5.8665809 ## Pontiac Firebird 2.4927415 5.7801212 ## Fiat X1-9 17.4183272 21.1153810 18.5836971 ## Porsche 914-2 15.1424331 18.1679491 16.0279956 6.9673761 ## Lotus Europa 17.0334994 20.2828613 17.9190619 5.4345617 ## Ford Pantera L 11.9334660 7.5252203 12.4595972 18.4134583 ## Ferrari Dino 13.2712830 12.1594541 13.4275878 14.5546093 ## Maserati Bora 13.5634873 10.2659381 14.7712191 22.7557478 ## Volvo 142E 13.8788532 17.5759070 15.0442231 3.6516910 ## Porsche 914-2 Lotus Europa Ford Pantera L Ferrari Dino ## Mazda RX4 Wag ## Datsun 710 ## Hornet 4 Drive ## Hornet Sportabout ## Valiant ## Duster 360 ## Merc 240D ## Merc 230 ## Merc 280 ## Merc 280C ## Merc 450SE ## Merc 450SL ## Merc 450SLC ## Cadillac Fleetwood ## Lincoln Continental ## Chrysler Imperial ## Fiat 128 ## Honda Civic ## Toyota Corolla ## Toyota Corona ## Dodge Challenger ## AMC Javelin ## Camaro Z28 ## Pontiac Firebird ## Fiat X1-9 ## Porsche 914-2 ## Lotus Europa 5.2254313 ## Ford Pantera L 12.2316006 16.0297667 ## Ferrari Dino 8.8964305 11.0113428 8.0559820 ## Maserati Bora 17.0975690 19.2124813 5.7847419 8.2011385 ## Volvo 142E 6.6867056 5.9981179 14.7617674 11.0355756 ## Maserati Bora ## Mazda RX4 Wag ## Datsun 710 ## Hornet 4 Drive ## Hornet Sportabout ## Valiant ## Duster 360 ## Merc 240D ## Merc 230 ## Merc 280 ## Merc 280C ## Merc 450SE ## Merc 450SL ## Merc 450SLC ## Cadillac Fleetwood ## Lincoln Continental ## Chrysler Imperial ## Fiat 128 ## Honda Civic ## Toyota Corolla ## Toyota Corona ## Dodge Challenger ## AMC Javelin ## Camaro Z28 ## Pontiac Firebird ## Fiat X1-9 ## Porsche 914-2 ## Lotus Europa ## Ford Pantera L ## Ferrari Dino ## Maserati Bora ## Volvo 142E 19.2162737
Hierarchical Clustering -hclust()
用hclust函數畫圖，必要參數是個觀察職的距離（可用dist()函數計算）
par(mar=rep(2,4),mfrow=c(1,1)) hc<-hclust(dist(mtcars.mxs)) #可用method參數設定聚合方法，預設為complete plot(hc)
Hierarchical Clustering -hclust()
用hclust函數畫圖，必要參數是個觀察職的距離（可用dist()函數計算）
par(mar=rep(2,4),mfrow=c(1,1)) hc<-hclust(dist(mtcars.mxs),method="average") #聚合方法為計算平均距離 plot(hc)
Hierarchical Clustering -cutree()
clusterCut <- cutree(hc, k=5) #分5群 sort(clusterCut)
## Mazda RX4 Mazda RX4 Wag Porsche 914-2 ## 1 1 1 ## Ferrari Dino Datsun 710 Fiat 128 ## 1 2 2 ## Honda Civic Toyota Corolla Fiat X1-9 ## 2 2 2 ## Lotus Europa Volvo 142E Hornet 4 Drive ## 2 2 3 ## Valiant Merc 240D Merc 230 ## 3 3 3 ## Merc 280 Merc 280C Toyota Corona ## 3 3 3 ## Hornet Sportabout Duster 360 Merc 450SE ## 4 4 4 ## Merc 450SL Merc 450SLC Cadillac Fleetwood ## 4 4 4 ## Lincoln Continental Chrysler Imperial Dodge Challenger ## 4 4 4 ## AMC Javelin Camaro Z28 Pontiac Firebird ## 4 4 4 ## Ford Pantera L Maserati Bora ## 5 5
HC- clusters & variables
ggplot()+geom_point(data=mtcars,
aes(x=hp,y=mpg,color=as.factor(clusterCut)))
Hierarchical Clustering -cutree(),2
clusterCut <- cutree(hc,h =4) #切在高度=4的地方（距離=4） sort(clusterCut)
## Mazda RX4 Mazda RX4 Wag Datsun 710 ## 1 1 1 ## Fiat 128 Honda Civic Toyota Corolla ## 1 1 1 ## Fiat X1-9 Porsche 914-2 Lotus Europa ## 1 1 1 ## Ferrari Dino Volvo 142E Hornet 4 Drive ## 1 1 2 ## Valiant Merc 240D Merc 230 ## 2 2 2 ## Merc 280 Merc 280C Toyota Corona ## 2 2 2 ## Hornet Sportabout Duster 360 Merc 450SE ## 3 3 3 ## Merc 450SL Merc 450SLC Cadillac Fleetwood ## 3 3 3 ## Lincoln Continental Chrysler Imperial Dodge Challenger ## 3 3 3 ## AMC Javelin Camaro Z28 Pontiac Firebird ## 3 3 3 ## Ford Pantera L Maserati Bora ## 4 4
Cluster the data -heatmap(),2
par(mar=rep(0.2,4),mfrow=c(1,1)) heatmap(mtcars.mxs)
Hierarchical clustering - hclust
distxy <- dist(mtcars.mxs) hClustering <- hclust(distxy) plot(hClustering)
Hierarchical clustering: summary
可快速瀏覽觀察值與各欄位的關係
- 分群結果可能被以下參數影響：
- 計算距離的方法
- 分群依據
- 更改數值的大小
- 可能會遇到的問題：
- 有時會不太清楚要如何切割分群結果
K-means clustering
- 執行步驟
- 指定要分幾群
- 計算每一群的中心點
- 將各個物件/觀察值指定給最近的中心點
- 依照新的分群計算新的中心點
K-means clustering
- 輸入
- 計算距離的資料（數值）
- 要分成幾群 # of clusters
- 預設個群的中間點位置
- 產出
- 計算出每’群‘的中心點
- 指定每個觀察值所在的’群‘
K-means clustering - example
x<-scale(mtcars$hp[-1]);y<-scale(mtcars$mpg[-1]) plot(x,y,col="blue",pch=19,cex=2) text(x+0.05,y+0.05,labels=labelCar)
K-means - starting centroids
K-means - assign to closest centroid
K-means - recalculate centroids
K-means - reassign values
K-means - update centroids
kmeans() -1
- Important parameters:
x,centers,iter.max,nstart
dataFrame <- data.frame(x,y) kmeansObj <- kmeans(dataFrame,centers=3) names(kmeansObj)
## [1] "cluster" "centers" "totss" "withinss" ## [5] "tot.withinss" "betweenss" "size" "iter" ## [9] "ifault"
kmeansObj$cluster
## [1] 3 3 3 2 3 2 3 3 3 3 2 2 2 2 2 2 1 1 1 3 2 2 2 2 1 1 1 2 2 2 3
kmeans() -2
par(mar=rep(0.2,4)) plot(x,y,col=kmeansObj$cluster,pch=19,cex=2) points(kmeansObj$centers,col=1:3,pch=3,cex=3,lwd=3)
Heatmaps
set.seed(1234) dataMatrix <- as.matrix(dataFrame)[sample(1:12),] kmeansObj <- kmeans(dataMatrix,centers=3) par(mfrow=c(1,2), mar = c(2, 4, 0.1, 0.1)) image(t(dataMatrix)[,nrow(dataMatrix):1],yaxt="n") image(t(dataMatrix)[,order(kmeansObj$cluster)],yaxt="n")
K-means注意事項
- 需要決定# of clusters
- 用眼睛/人工/特殊要求選
- 用 cross validation/information theory選
- Determining the number of clusters
- K-means 沒有一定的結果
- 不同的 # of clusters
- 不同的 # of iterations
Use sum of squared error (SSE) scree plot to optimize the number of clusters
SSE: The sum of the squared distance between each member of a cluster and its cluster centroid.
SSE scree plot
par(mfrow=c(1,1), mar = c(4,4,1,1)) #下,左,上,右
wss <- (nrow(dataMatrix)-1)*sum(apply(dataMatrix,2,var))
for (i in 2:(nrow(dataMatrix)-1)) {
wss[i] <- sum(kmeans(dataMatrix,centers=i)$withinss)
}
plot(1:(nrow(dataMatrix)-1), wss, type="b", xlab="Number of Clusters",
ylab="Within groups sum of squares")
Missing values
dataMatrix2 <- mtcars.mx ## Randomly insert some missing data dataMatrix2[sample(1:100,size=10,replace=FALSE)] <- NA head(dataMatrix2,10)
## mpg cyl disp hp drat wt qsec vs am gear carb ## Mazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4 ## Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4 ## Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1 ## Hornet 4 Drive 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1 ## Hornet Sportabout 18.7 NA 360.0 175 3.15 3.440 17.02 0 0 3 2 ## Valiant 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1 ## Duster 360 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4 ## Merc 240D 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2 ## Merc 230 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2 ## Merc 280 19.2 6 167.6 123 3.92 3.440 18.30 1 0 4 4
Imputing {impute}
用knn的方法計算空值可能可以帶入的數值
#source("https://bioconductor.org/biocLite.R")
#biocLite("impute")
library(impute)
dataMatrix2 <- impute.knn(dataMatrix2)$data
head(dataMatrix2,10)
## mpg cyl disp hp drat wt qsec vs am gear carb ## Mazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4 ## Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4 ## Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1 ## Hornet 4 Drive 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1 ## Hornet Sportabout 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2 ## Valiant 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1 ## Duster 360 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4 ## Merc 240D 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2 ## Merc 230 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2 ## Merc 280 19.2 6 167.6 123 3.92 3.440 18.30 1 0 4 4